TechyCSR/OpenCluely

OpenCluely is a free, open source Cluely (alternative), built for technical interviews like DSA, OAs, and CP. It offers an invisible overlay, real-time AI help, Smart Image Processing for question capture, and multi-language support : 100% customizable and private.

What it solves

OpenCluely provides a discreet, real-time AI assistant for technical interviews and practice. It helps users by providing instant answers to questions via voice or screenshots, displaying them in a way that remains invisible to screen-sharing and recording software on Windows and macOS.

How it works

The application uses a stealth overlay that sits on top of your screen. You can trigger it by speaking (using local Whisper or Azure Speech) or by taking a screenshot. These inputs are sent to Google Gemini, which processes the request using your full conversation history. The AI then streams the answer back to a floating window or chat panel on your screen, featuring syntax-highlighted code blocks.

Who it’s for

It is designed for individuals who want an AI-powered practice tool for technical interviews. It is particularly useful for those who need to reference code or concepts during a session without their screen-sharing software capturing the assistant's output.

Highlights

  • Invisible overlay: Windows remain hidden from Zoom, Google Meet, Teams, Discord, and OBS captures on Windows and macOS.
  • Direct image analysis: Screenshots are sent directly to Gemini for visual reasoning, bypassing slow OCR processes.
  • Flexible voice input: Supports local Whisper for offline transcription or Azure Speech, with configurable voice-activity detection.
  • Session context: The app remembers your conversation history, allowing for follow-up questions and complex technical discussions.
  • Privacy-focused: The software collects no telemetry, runs locally, and keeps your session data on your own device.

Related

  • Project
    EuniAI/Prometheus

    An AI-powered software engineering platform that uses multi-agent systems and knowledge graphs to automate bug fixing, feature implementation, and codebase navigation.

  • Project
    dagoSte/squadra

    Squadra coordinates multiple AI coding agents (Claude Code, Codex, Cursor) on one project. It maintains a shared registry of tasks, reviews, and decisions, ensuring independent review and proof for each change, with a local dashboard to track progress.

  • Project
    lee-to/ai-factory

    AI Factory is an npm CLI that instantly equips a codebase with AI coding agents and pre‑built prompt “skills”. After `ai-factory init` it configures agents (Claude, Codex, Gemini, etc.), installs community‑sourced skills, and provides slash‑command workflows (/aif‑plan, /aif‑implement, /aif‑fix, …) to research, plan, implement, and document features with AI‑generated commits and quality‑gate reports.

  • Project
    DeepMyst/Mysti

    An open-source VS Code workspace that coordinates multiple AI coding agents, allowing for parallel opinions, sequential handoffs, and structured brainstorming.